pin-check
Skill0 starsChanged 6 days agoMITView on GitHub
Reverts a line, runs the scoped test and reports whether it pins the behaviour. Use when the user asks if a test catches a change. Not for mutation scoring.
In this repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- claude-arsenal/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- coverage-gapsSkill
- dep-upgradeSkill
- designSkill
- executionSkill
- explore-ideaSkill
- gate-checkSkill
- githubSkill
- initSkill
- litcriticSkill
- mutmut-reportSkill
- pypi-releaseSkill
- python-bootstrapSkill
- queue-addSkill
- queue-nextSkill
- queue-statusSkill
- reviewSkill
- session-endSkill
- shipSkill
- specifySkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 35
Use the script rather than a hand sed cycle: it purges __pycache__, runs each test in a fresh subprocess, refuses a target that matches …
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
pin-check
One deliberate mutation per claim, aimed at one test: is this behaviour pinned,
or merely true? coverage-gaps answers whether a line ran and mutmut-report
scores thousands of automatic mutants; this answers one claim in seconds.
CANARY: pin-check-loaded-2026-09-15-1c4de0b7-9a2f61d08e4b7c35
Step 1 — Name the claim and its one test
Give the exact text the claim is about and the one test that should catch it changing. Scoping to that test keeps a run to seconds.
python3 "${CLAUDE_SKILL_DIR}/scripts/pin_check.py" \
--source src/yourproject/rules.yaml \
--replace "asynchronous" --with "async" \
--test tests/<the-one-case>.py--expect-count N refuses to run unless the target occurs exactly N times, so
one claim stays one mutation. --root DIR (repeatable) names extra trees to
purge bytecode from. Arguments after the flags go to pytest.
Use the script rather than a hand sed cycle: it purges __pycache__, runs
each test in a fresh subprocess, refuses a target that matches nothing, and
restores the file when the run ends; after a killed run, its sentinel makes the
next run refuse to start and print the manual restore command. A hand cycle gets
each of these wrong without noticing.
Step 2 — Read the verdict
| verdict | exit | means |
PINNED | 0 | the target changed and the scoped test went red; the claim holds |
NOT PINNED | 1 | the test stayed green; it asserts something true, not something pinned |
NOT MUTATED | 3 | the target was absent or matched a different count than --expect-count; nothing was tested |
INCONCLUSIVE | 4 | the test was already red before the mutation, or the file could not be restored |
| error | 2 | bad arguments, or a sentinel from a killed run is on disk (the message says how to restore) |
Step 3 — Act on it
NOT PINNED→ add an assertion on the value that changed, or a case that exercises the path, then re-run untilPINNED.PINNED→ cite it in the review.- Either way, report the mutation — source, target, replacement, test — with the verdict, since the verdict is only as good as the mutation.
Files outside version control, or generated files, cannot be safely restored; check them in first.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

